Mediated probabilities of causation
We propose a set of causal estimands that we call “the mediated probabilities of causation.” These estimands quantify the probabilities that an observed negative outcome was induced via a mediating pathway versus a direct pathway in a stylized setting involving a binary exposure or intervention, a s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2025-05-01
|
| Series: | Journal of Causal Inference |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jci-2024-0019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733711394766848 |
|---|---|
| author | Rubinstein Max Cuellar Maria Malinsky Daniel |
| author_facet | Rubinstein Max Cuellar Maria Malinsky Daniel |
| author_sort | Rubinstein Max |
| collection | DOAJ |
| description | We propose a set of causal estimands that we call “the mediated probabilities of causation.” These estimands quantify the probabilities that an observed negative outcome was induced via a mediating pathway versus a direct pathway in a stylized setting involving a binary exposure or intervention, a single binary mediator, and a binary outcome. We outline a set of conditions sufficient to identify these effects given observed data and propose a doubly robust projection-based estimation strategy that allows for the use of flexible nonparametric and machine learning methods for estimation. We argue that these effects may be more relevant than the probability of causation, particularly in settings where we observe both some negative outcome and negative mediating event, and we wish to distinguish between settings where the outcome was induced via the exposure inducing the mediator versus the exposure inducing the outcome directly. We motivate these estimands by discussing applications to legal and medical questions of causal attribution. |
| format | Article |
| id | doaj-art-c2a523c5c8df47c1aef44af6f4f90bec |
| institution | DOAJ |
| issn | 2193-3685 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Causal Inference |
| spelling | doaj-art-c2a523c5c8df47c1aef44af6f4f90bec2025-08-20T03:07:58ZengDe GruyterJournal of Causal Inference2193-36852025-05-011313455710.1515/jci-2024-0019Mediated probabilities of causationRubinstein Max0Cuellar Maria1Malinsky Daniel2RAND Corporation, Pittsburgh, PA, USADepartment of Criminology and Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, Pennsylvania, United StatesDepartment of Biostatistics, Columbia University, New York, United StatesWe propose a set of causal estimands that we call “the mediated probabilities of causation.” These estimands quantify the probabilities that an observed negative outcome was induced via a mediating pathway versus a direct pathway in a stylized setting involving a binary exposure or intervention, a single binary mediator, and a binary outcome. We outline a set of conditions sufficient to identify these effects given observed data and propose a doubly robust projection-based estimation strategy that allows for the use of flexible nonparametric and machine learning methods for estimation. We argue that these effects may be more relevant than the probability of causation, particularly in settings where we observe both some negative outcome and negative mediating event, and we wish to distinguish between settings where the outcome was induced via the exposure inducing the mediator versus the exposure inducing the outcome directly. We motivate these estimands by discussing applications to legal and medical questions of causal attribution.https://doi.org/10.1515/jci-2024-0019mediation analysisprobability of causationmachine learningnonparametricscausal inference62g0562d20 |
| spellingShingle | Rubinstein Max Cuellar Maria Malinsky Daniel Mediated probabilities of causation Journal of Causal Inference mediation analysis probability of causation machine learning nonparametrics causal inference 62g05 62d20 |
| title | Mediated probabilities of causation |
| title_full | Mediated probabilities of causation |
| title_fullStr | Mediated probabilities of causation |
| title_full_unstemmed | Mediated probabilities of causation |
| title_short | Mediated probabilities of causation |
| title_sort | mediated probabilities of causation |
| topic | mediation analysis probability of causation machine learning nonparametrics causal inference 62g05 62d20 |
| url | https://doi.org/10.1515/jci-2024-0019 |
| work_keys_str_mv | AT rubinsteinmax mediatedprobabilitiesofcausation AT cuellarmaria mediatedprobabilitiesofcausation AT malinskydaniel mediatedprobabilitiesofcausation |